Showing papers by "Tulay Adali published in 2018"

A Shared Vision for Machine Learning in Neuroscience

Abstract: With ever-increasing advancements in technology, neuroscientists are able to collect data in greater volumes and with finer resolution. The bottleneck in understanding how the brain works is consequently shifting away from the amount and type of data we can collect and toward what we actually do with the data. There has been a growing interest in leveraging this vast volume of data across levels of analysis, measurement techniques, and experimental paradigms to gain more insight into brain function. Such efforts are visible at an international scale, with the emergence of big data neuroscience initiatives, such as the BRAIN initiative (Bargmann et al., 2014), the Human Brain Project, the Human Connectome Project, and the National Institute of Mental Health9s Research Domain Criteria initiative. With these large-scale projects, much thought has been given to data-sharing across groups (Poldrack and Gorgolewski, 2014; Sejnowski et al., 2014); however, even with such data-sharing initiatives, funding mechanisms, and infrastructure, there still exists the challenge of how to cohesively integrate all the data. At multiple stages and levels of neuroscience investigation, machine learning holds great promise as an addition to the arsenal of analysis tools for discovering how the brain works.

Application of Graph Theory to Assess Static and Dynamic Brain Connectivity: Approaches for Building Brain Graphs

Abstract: Human brain connectivity is complex. Graph-theorybased analysis has become a powerful and popular approach for analyzing brain imaging data, largely because of its potential to quantitatively illuminate the networks, the static architecture in structure and function, the organization of dynamic behavior over time, and disease related brain changes. The first step in creating brain graphs is to define the nodes and edges connecting them. We review a number of approaches for defining brain nodes including fixed versus data-driven nodes. Expanding the narrow view of most studies which focus on static and/or single modality brain connectivity, we also survey advanced approaches and their performances in building dynamic and multimodal brain graphs. We show results from both simulated and real data from healthy controls and patients with mental illnesses. We outline the advantages and challenges of these various techniques. By summarizing and inspecting recent studies which analyzed brain imaging data based on graph theory, this paper provides a guide for developing new powerful tools to explore complex brain networks.

A window-less approach for capturing time-varying connectivity in fMRI data reveals the presence of states with variable rates of change.

Abstract: Functional connectivity during the resting state has been shown to change over time (i.e., has a dynamic connectivity). However, resting-state fluctuations, in contrast to task-based experiments, are not initiated by an external stimulus. Consequently, a more complicated method needs to be designed to measure the dynamic connectivity. Previous approaches have been based on assumptions regarding the nature of the underlying dynamic connectivity to compensate for this knowledge gap. The most common assumption is what we refer to as locality assumption. Under a locality assumption, a single connectivity state can be estimated from data that are close in time. This assumption is so natural that it has been either explicitly or implicitly embedded in many current approaches to capture dynamic connectivity. However, an important drawback of methods using this assumption is they are unable to capture dynamic changes in connectivity beyond the embedded rate while, there has been no evidence that the rate of change in brain connectivity matches the rates enforced by this assumption. In this study, we propose an approach that enables us to capture functional connectivity with arbitrary rates of change, varying from very slow to the theoretically maximum possible rate of change, which is only imposed by the sampling rate of the imaging device. This method allows us to observe unique patterns of connectivity that were not observable with previous approaches. As we explain further, these patterns are also significantly correlated to the age and gender of study subjects, which suggests they are also neurobiologically related.

Resting-State fMRI Dynamics and Null Models: Perspectives, Sampling Variability, and Simulations.

Abstract: Studies of resting state functional MRI (rs-fRMI) are increasingly focused on “dynamics”, or on those properties of brain activation that manifest and vary on timescales shorter than the scan’s full duration. This shift in focus has led to a flurry of interest in developing hypothesis testing frameworks and null models applicable to the dynamical setting. Thus far however, these efforts have been weakened by a number of crucial shortcomings that are outlined and discussed in this short paper. We focus here on aspects of recently proposed null models that, we argue, are poorly formulated relative to the hypotheses they are designed to test, i.e. their potential role in separating functionally relevant BOLD signal dynamics from noise or intermittent background and maintenance type processes is limited by factors that are fundamental rather than merely quantitative or parametric. In this short position paper, we emphasize that (1) serious care must be exercised in building null models for rs-fMRI dynamics from distributionally stationary univariate or multivariate timeseries, i.e. timeseries whose values are each independently drawn from one pre-specified probability distribution; and (2) measures such as kurtosis that quantify over-concentration of observed values in the far tails of some reference distribution may not be particularly suitable for capturing signal features most plausibly contributing to functionally relevant brain dynamics. Other metrics targeted, for example, at capturing the epochal temporal variation that contributes heavily to dynamic functional connectivity estimates and is and often taken as a signature of brain responsiveness to stimuli or experimental tasks, could play a more scientifically clarifying role. As we learn more about the phenomenon of functionally relevant brain dynamics and its imaging correlates, scientifically meaningful null hypotheses and well-tuned null models will naturally emerge. We also revisit the important concept of distributional stationarity, discuss how it manifests within realizations versus across multiple realizations, and provide guidance on the benefits and limitations of employing this type of stationarity in modeling the absence of functionally relevant temporal dynamics in resting state fMRI. We hope that the discussions herein are useful, and promote thoughtful consideration of these important issues.

Consistent Run Selection for Independent Component Analysis: Application to Fmri Analysis

Abstract: Independent component analysis (ICA) has found wide application in a variety of areas, and analysis of functional magnetic resonance imaging (fMRI) data has been a particularly fruitful one. Maximum likelihood provides a natural formuiation for ICA and allows one to take into account multiple statistical properties of the data-forms of diversity. While use of multiple types of diversity allows for additional flexibility, it comes at a cost, leading to high variability in the solution space. In this paper, using simulated as well as fMRI-like data, we provide insight into the trade-offs between estimation accuracy and algorithmic consistency with or without deviations from the assumed model and assumptions such as the statistical independence. Additionally, we propose a new metric, cross inter-symbol interference, to quantify the consistency of an algorithm across different runs, and demonstrate its desirable performance for selecting consistent run compared to other metrics used for the task.

Shared and Subject-Specific Dictionary Learning (ShSSDL) Algorithm for Multisubject fMRI Data Analysis

Abstract: Objective: Analysis of functional magnetic resonance imaging (fMRI) data from multiple subjects is at the heart of many medical imaging studies, and approaches based on dictionary learning (DL) are recently noted as promising solutions to the problem. However, the DL-based methods for fMRI analysis proposed to date do not naturally extend to multisubject analysis. In this paper, we propose a DL algorithm for multisubject fMRI data analysis. Methods: The proposed algorithm [named shared and subject-specific dictionary learning (ShSSDL)] is derived based on a temporal concatenation, which is particularly attractive for the analysis of multisubject task-related fMRI datasets. It differs from existing DL algorithms in both its sparse coding and dictionary update stages and has the advantage of learning a dictionary shared by all subjects as well as a set of subject-specific dictionaries. Results: The performance of the proposed DL algorithm is illustrated using simulated and real fMRI datasets. The results show that it can successfully extract shared as well as subject-specific latent components. Conclusion: In addition to offering a new DL approach, when applied on multisubject fMRI data analysis, the proposed algorithm generates a group level as well as a set of subject-specific spatial maps. Significance: The proposed algorithm has the advantage of learning simultaneously multiple dictionaries providing us with a shared as well discriminative source of information about the analyzed fMRI datasets.

Consecutive Independence and Correlation Transform for Multimodal Fusion: Application to Eeg and Fmri Data

Abstract: Methods based on independent component analysis (ICA) and canonical correlation analysis (CCA) as well as their various extensions have become popular for the fusion of multimodal data as they minimize assumptions about the relationships among multiple datasets. Two important extensions that are widely used, joint ICA (jICA) and parallel ICA (pICA), make a number of simplifying assumptions that might limit their usefulness such as identical mixing matrices for jICA, and the requirement for the same number of components for jICA and pICA. In this paper, we propose a new, flexible hybrid method for fusion based on ICA and CCA, called consecutive independence and correlation transform (C-ICT), which relaxes the main limitations of jICA and pICA. We demonstrate performance advantages of C-ICT both through simulations and application to real medical data collected from schizophrenia patients and healthy controls performing an auditory oddball task (AOD).

Applications of Graph Theory

Abstract: Graph-theoretical methods are being increasingly used in areas of interest within the IEEE and beyond. Graphs are mathematical abstractions that can be used to represent networks of various types: physical (e.g., the internet or electrical networks), biological (e.g., brain networks), or social (e.g., online social networks). Furthermore, graphs can provide tools for flexible representation of data sets in which data points have irregular positions with respect to each other. Common examples of this include data sets acquired by a sensor network, where uniform sensor placement may not be possible, or machine learning data sets, where training samples are not uniformly distributed in feature space. In some instances, a graph representation arises as a natural way to describe the problem, while in other areas, e.g., image processing, they are being used to develop powerful, content-dependent alternatives to conventional processing tools.

The Dangers of Following Trends in Research: Sparsity and Other Examples of Hammers in Search of Nails

Abstract: Trends, they are not only for the fashion industry after all. Within the engineering and computer science research communities as well, we periodically observe the phenomenon, see how certain methods suddenly start receiving particular attention, and sometimes, even though they emerge as an attractive solution for a given set of problems, they tend to become a hammer looking for new nails. At first, using a new method on old problems is the natural and reasonable way to proceed. There have been remarkable successes achieved through the adoption of a tool from another field or a new way of looking at old problems that brings new insights and solutions.

Independent Vector Analysis for SSVEP Signal Enhancement, Detection, and Topographical Mapping

Abstract: Steady state visual evoked potentials (SSVEPs) have been identified as an effective solution for brain computer interface (BCI) systems as well as for neurocognitive investigations. SSVEPs can be observed in the scalp-based recordings of electroencephalogram signals, and are one component buried amongst the normal brain signals and complex noise. We present a novel method for enhancing and improving detection of SSVEPs by leveraging the rich joint blind source separation framework using independent vector analysis (IVA). IVA exploits the diversity within each dataset while preserving dependence across all the datasets. This approach is shown to enhance the detection of SSVEP signals across a range of frequencies and subjects for BCI systems. Furthermore, we show that IVA enables improved topographic mapping of the SSVEP propagation providing a promising new tool for neuroscience and neurocognitive research.

Independent Component Analysis Using Semi-Parametric Density Estimation Via Entropy Maximization

Abstract: Independent component analysis (ICA) is one of the most popular methods for blind source separation with a diverse set of applications, such as: biomedical signal processing, video and image analysis, and communications. The success of ICA is tied to proper characterization of the probability density function (PDF) of the latent sources; information that is generally unknown. In this work, we propose a new and efficient ICA algorithm based on entropy maximization with kernels, (ICA-EMK), which uses both global and local measuring functions as constraints to dynamically estimate the PDF of the sources. We present a mathematical justification of its convergence and demonstrate its superior performance over competing ICA algorithms using simulated as well as real-world data.

Capturing Common and Individual Components in fMRI Data by Discriminative Dictionary Learning

Abstract: Data-driven analysis for functional magnetic resonance imaging (fMRI) data has played an important role for uncovering salient brain functional networks that are shared across multiple subjects. On the other hand, recent fMRI studies indicate that there is significant and consistent heterogeneity present across different subject groups and individuals. While independent component analysis (ICA) has been a major tool to perform data-driven analysis of fMRI data, dictionary learning (DL) approaches are increasingly receiving attention due to their modeling capability and flexibility. In this work, a supervised DL framework is employed to capitalize on the available class labels and capture not only the commonly shared components across the population, but also the unique components that contribute to discrimination. A systematic comparison with conventional ICA is performed based on real fMRI data consisting of healthy controls and patients with schizophrenia.

Evaluating Models of Dynamic Functional Connectivity Using Predictive Classification Accuracy

Abstract: Dynamic functional connectivity has become a prominent approach for tracking the changes of macroscale statistical dependencies between regions in the brain. Effective parametrization of these statistical dependencies, referred to as brain states, is however still an open problem. We investigate different emission models in the hidden Markov model framework, each representing certain assumptions about dynamic changes in the brain. We evaluate each model by how well they can discriminate between schizophrenic patients and healthy controls based on a group independent component analysis of resting-state functional magnetic resonance imaging data. We find that simple emission models without full covariance matrices can achieve similar classification results as the models with more parameters. This raises questions about the predictability of dynamic functional connectivity in comparison to simpler dynamic features when used as biomarkers. However, we must stress that there is a distinction between characterization and classification, which has to be investigated further.

A Shared Vision for Machine Learning in Neuroscience

Abstract: With ever-increasing advancements in technology, neuroscientists are able to collect data in greater volumes and with finer resolution. The bottleneck in understanding how the brain works is consequently shifting away from the amount and type of data we can collect and toward what we actually do with the data. There has been a growing interest in leveraging this vast volume of data across levels of analysis, measurement techniques, and experimental paradigms to gain more insight into brain function. Such efforts are visible at an international scale, with the emergence of big data neuroscience initiatives, such as the BRAIN initiative (Bargmann et al., 2014), the Human Brain Project, the Human Connectome Project, and the National Institute of Mental Health9s Research Domain Criteria initiative. With these large-scale projects, much thought has been given to data-sharing across groups (Poldrack and Gorgolewski, 2014; Sejnowski et al., 2014); however, even with such data-sharing initiatives, funding mechanisms, and infrastructure, there still exists the challenge of how to cohesively integrate all the data. At multiple stages and levels of neuroscience investigation, machine learning holds great promise as an addition to the arsenal of analysis tools for discovering how the brain works.

IVA-Based Spatio-Temporal Dynamic Connectivity Analysis in Large-Scale FMRI Data

Abstract: Recently, much attention has been devoted to examining time-varying changes in functional connectivity to understand the network structure in the human brain Most studies, however, analyze the time-varying functional connectivity but ignore the time-varying spatial information In this paper, we propose a method based on independent vector analysis (IVA) to study dynamic functional network connectivity (dFNC) as well as dynamic spatial functional network connectivity (dsFNC) in fMRI data Though IVA allows one to effectively capture both, its performance degrades with the increase in the number of datasets Hence, we propose an effective scheme to bypass this limitation followed by graph theoretical analysis to study both inter-network dynamics and intra-network stationarity We observe higher dFNC fluctuations for patients with schizophrenia in the default-mode (DM)-salience network and cerebellum with associated connections dsFNC analysis indicates higher inter-network fluctuation in patients while DM, anterior DM and frontal networks demonstrate significant intra-network fluctuation in controls

A two-level ICA approach reveals important differences in the female brain response to thermal pain

Abstract: Pain is subjective, while pain neuroimaging analysis methods need to be as objective as possible. Most neuroimaging studies use a general linear model (GLM) approach which heavily relies on a number of key assumptions. Independent component analysis (ICA), on the other hand, is a data-driven approach and hence significantly reduces need for specific assumptions such as Gaussian distributed residuals and the definition of user-specified design matrix, both required by the GLM. In this paper, we propose a two-level ICA-based method as an attractive alternative, and apply it to the analysis of functional magnetic resonance imaging (fMRI) data acquired during thermal pain stimuli. We identify distinct female brain responses in parts of the "pain matrix", operculum (secondary somatosensory cortex, SII), anterior insular (AI), dorsal anterior cingular cortex (dACC), and default mode network (DMN). We also show that this pain and DMN network have significant correlation with behavioral measures.

Power spectra constrained IVA for SSVEP detection

Abstract: The detection of steady state visual evoked potentials (SSVEPs), an evoked response to visual stimuli, has been identified as an effective solution for brain computer interface systems and as a probe for neurocognitive investigations of visually related tasks. However, since they recorded as part of the scalp-based electroencephalogram (EEG) signals their detection is challenging as they are buried amongst the normal brain signals. Blind source separation methods, such as independent vector analysis (IVA), have been shown to be capable of enhancing and improving signal detection by exploiting the diversity within individual datasets while simultaneously exploiting the complimentary information across datasets. In general, IVA is highly flexible with a general solution space; however, it is not guaranteed to converge to a meaningful minimum, by incorporating a problem specific constraint we can shrink the solution space insuring a relevant solution. In this work, we present a novel multiset data framework for EEG recordings and apply our constrained power spectra IVA (CP-IVA) to a publicly available SSVEP dataset. We compare the prediction accuracy of CP-IVA with that of an optimized processing stream developed for that dataset, as well as a canonical correlation analysis (CCA) based approach, showing that CP-IVA achieves better average performance and is more robust across the population of subjects with a higher minimum detection rate. More importantly, CP-IVA achieves this performance with minimal pre-processing and without the need to train complex classifiers.